NetEase Youdao open-sources Confucius4-R2T2, a 1.7B real-time streaming ASR model for voice agents
_akhaliq · x · 2026-09-18
NetEase Youdao has open-sourced Confucius4-R2T2, a 1.7B-parameter true streaming ASR model built for voice agents.
Key points:
- Fine-grained, configurable decoding chunks from 80ms to 2s, delivering low latency and high accuracy
- Append-only output mode: transcript text is committed permanently without revising previous words, avoiding flickering and disruptive rewrites in real-time UIs
- Targets live captioning, downstream NLP/LLM agent pipelines, and simultaneous speech translation
Code and weights are available on GitHub and Hugging Face, with WebSocket server/client examples included.
Related event: NetEase Youdao Open-Sources Streaming ASR Model Confucius4-R2T2(21 posts)→
More from Models
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02